© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70450
    Prev
    Next
    INDEX
    Explanations

    multi-language text fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ✨:
    -1.20
    UNCIL
    -1.12
    会の
    -1.06
    🗺
    -1.06
    .}~\
    -1.05
     mágica
    -1.05
    legging
    -1.05
     Economía
    -1.04
    TAWA
    -1.04
     gwaran
    -1.03
    POSITIVE LOGITS
     refirió
    1.34
    Descriere
    1.30
     probabilmente
    1.22
    似乎
    1.20
     sicuramente
    1.19
     crescita
    1.16
     affez
    1.13
     disponibilità
    1.11
     quadrinhos
    1.10
    َا
    1.08
    Activations Density 0.000%

    No Known Activations